Agent skill

Novel Characters

by suihe1 in suihe1/short-drama-production

从故事中整理人物身份、关系、外观和声线设计,产出角色卡、图像提示词与评审报告,可按需生成设定图。用于角色分析、人物画像和角色母本;短剧制作中按已批准大纲与当前批次选角。

Apache-2.0Auto-check: notesMedia & Creative

Install Novel Characters

skills CLI
$ npx skills add suihe1/short-drama-production --skill novel-characters -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install suihe1/short-drama-production novel-characters --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/suihe1/short-drama-production.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/novel-characters .claude/skills/novel-characters && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
novel-characters
GitHub stars
181
Token cost
~1.8k tokens
SKILL.md length
324 words
Files
16 (incl. scripts, references, assets)
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

从故事中整理人物身份、关系、外观和声线设计,产出角色卡、图像提示词与评审报告,可按需生成设定图。用于角色分析、人物画像和角色母本;短剧制作中按已批准大纲与当前批次选角。

  • Works in 12 steps: 确定报告语言 → 5 — 确定画风 → 定位输入 → …
  • Tasks that involve Creative writing and fiction
  • SKILL.md covers 输入与创作权限, novel-characters, 边界 and 自测, plus 2 more sections
  • Runs JavaScript scripts from its folder; calls node; needs OPENAI_API_KEY

What it does

Novel Characters is an agent skill from suihe1/short-drama-production. 从故事中整理人物身份、关系、外观和声线设计,产出角色卡、图像提示词与评审报告,可按需生成设定图。用于角色分析、人物画像和角色母本;短剧制作中按已批准大纲与当前批次选角。

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including scripts, reference files and assets (for example `README.en.md`, `README.md` and `examples/渡口-cast.json`).

It sits in Media & Creative, covering Creative writing and fiction. It works with MiniMax. The repository describes itself as: AI 短剧生产总控 / 短剧skill:专业导演与分镜、MiniMax H3、CompShare、声音资产、粗剪与 QC,默认 16:9。 The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Creative writing and fiction

Example prompts

  • “/novel-characters”

Requirements

  • Node.js
  • A credential in OPENAI_API_KEY
  • Pre-approved tools (allowed-tools): Read, Write, Bash, Task, Glob

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. 确定报告语言
  2. 5 — 确定画风
  3. 定位输入
  4. 分块
  5. 第一趟扫描(仅 N > 1)
  6. 归并 + 复核
  7. 选角
  8. 第二趟出卡
  9. 校验 ⛔ 不能跳
  10. 出图(可选,每个角色都出)
  11. 输出
  12. 汇报

What it can do on your machine

Read from SKILL.md and the folder at commit dbd3310. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Bash
    • Task
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Novel Characters loads about 1.8k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 25 tokens; SKILL.md has 324 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Bash, Task, Glob

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from suihe1/short-drama-production at commit dbd3310, republished under its Apache-2.0 licence (© suihe1). 324 words, ~1,783 tokens.

Download SKILL.mdSave it as .claude/skills/novel-characters/SKILL.md (or your agent's skills folder). This skill also uses 15 other files; get the full folder from GitHub.
name
novel-characters
description
从故事中整理人物身份、关系、外观和声线设计,产出角色卡、图像提示词与评审报告,可按需生成设定图。用于角色分析、人物画像和角色母本;短剧制作中按已批准大纲与当前批次选角。
allowed-tools
Read, Write, Bash, Task, Glob
metadata.license
Apache-2.0
metadata.runtimes
claude-code, codex
metadata.version
1.8.0
metadata.triggers
novel-characters, 拆角色, 拆书角色, 小说角色, 人物画像, 角色卡, 三视图, character sheet from novel

输入与创作权限

先读用户实际材料与目标,复用已确定的事实和规格;已有剧本、资产或分镜直接进入相关工作,不为流程完整重写上游。未授权的删线、合人、改变人物身份、主题、结局或重要表演意图,先展示原位置、具体方案与得失,再由用户选择;已授权的局部修正直接完成。

下面的类型经验、批次和创作预算是适配起点,不是用户接受过的创作要求。旧校验器可能仍将部分经验规则报为失败:区分实际数据/引用/模型接口错误与创作建议,说明不适用项,保留原稿;不伪造字段、不静默改戏或降低技术投产要求。总控可用时参考其 references/creative-agreement.md;独立任务按本段处理,不强制依赖总控。

novel-characters

输入一篇小说/短故事,输出每个角色的:人物画像、形象提示词、音色提示词、角色设定图。

{baseDir} = 本文件所在目录。脚本 {baseDir}/scripts/novel-characters.mjs,零依赖,node 直接跑。

运行环境:Claude Code 和 codex 都能跑。差别只在第 8 步出图——见 references/sheet.md。


Step 0 — 确定报告语言

用户可以指定语言,比如「用英文」「--lang en」「日本語で」。没说就是中文(zh)。

这个 lang 会一路传下去:第二趟生成角色卡时决定人类可读字段用什么语言,validate 和 render 也都要带上。

界面文案分两种情况:

  • zh / en / ja —— 内置,不用管

  • 其他任何语言 —— 你要现场翻一份。跑

    bash
    node {baseDir}/scripts/novel-characters.mjs ui-template <lang>

    它打印一份英文骨架,把每个值翻译成目标语言,整块放进 cast.json 顶层的 ui 字段。渲染时会合并进内置表。

    不给 ui 的话 validate 会直接报错——否则报告会是「角色内容是法语、界面标签是英文」的半吊子状态。

支持的语言不受内置表限制,法语韩语西班牙语都能出完整报告。

Step 0.5 — 确定画风

用户可以指定出图风格:默认 realistic(半写实厚涂),想要动画质感就用 ghibli(吉卜力式手绘赛璐璐)。

bash
node {baseDir}/scripts/novel-characters.mjs styles   # 打印预设的完整内容

读 {baseDir}/references/style-presets.md。换风格是整套换——每个预设自带 render / surface / lighting / negative / tags 五块,整块取用,不要混搭。

最容易搞反的是反向提示词:realistic 绝不能禁 photorealistic,ghibli 必须禁。validate 会拦这个。

版面规则(16:9 三区、比例、细节让位)不随风格变,变的只有渲染质感。

Step 1 — 定位输入

用户给文件路径就直接用。直接粘正文的,先落到一个临时 .txt——后面校验「引文是否逐字」要拿原文比对,没有原文文件这步就没法做。

确定输出目录:用户指定就用;没指定就用原书同级目录。

Step 2 — 分块
bash
node {baseDir}/scripts/novel-characters.mjs chunk <book.txt> <workdir>

打印 {"chunks": N, ...}。

  • N == 1:跳过 Step 3,直接在当前会话读原文做第一趟,结果自己写成 <workdir>/roster-00.json
  • N > 1:进 Step 3
  • truncated: true:明确告诉用户尾部没扫到,别闷着
Step 3 — 第一趟扫描(仅 N > 1)

当前环境支持子代理就并发(Claude Code 的 Task、codex 的 subagent):每块一个子代理,所有调用放在同一条消息里才是真并发。不支持就一块一块串行读,结果一样,只是慢。

每个子代理的任务:

  1. 读 {baseDir}/references/roster-pass.md,照它执行
  2. 读 <workdir>/chunk-NN.txt
  3. 把 roster JSON 写到 <workdir>/roster-NN.json
  4. 只回一句「done NN,抽到 X 个角色」
Step 4 — 归并 + 复核
bash
node {baseDir}/scripts/novel-characters.mjs merge <workdir> | tee <workdir>/merged.json

落到 merged.json 不只是留档:Step 6 的 assemble 靠它拿同档角色的戏份顺序。

按名字+别名精确收敛(某块把「陆」列成「陆行远」的别名,两条就并成一个人),notes 累加、quotes 去重,按出现块数降序——出现的块越多戏份越重。

输出是 { "characters": [...], "mergeCandidates": [...] }。mergeCandidates 要逐条复核:精确匹配只能收敛两块恰好写了相同称呼的情况,剩下的是语义判断,脚本做不了。候选来自名字包含关系(「陆」⊂「陆行远」)——是强信号不是判决,同姓的父子、兄弟就不能合。候选之外你自己看出来的同人(「陆先生」和「行远」没有包含关系,不会进候选)也要合。

要合并就写一份 merges.json 再落地:

json
{ "merges": [{ "keep": "陆行远", "absorb": ["陆", "陆先生"] }] }
bash
node {baseDir}/scripts/novel-characters.mjs merge <workdir> --apply merges.json | tee <workdir>/merged.json

keep/absorb 用名字或任一别名定位都行,找不到会直接报错。输出仍带 mergeCandidates,剩下的都确认是不同的人(或清空)再进下一步。没有要合的就直接往下走——但 merged.json 必须留着。

Step 5 — 选角

独立原文分析可按用户指定 N 位(未指定最多 30 位)整理。短剧制作中,以已批准大纲保留的角色为准,不把原著戏份排名当投产名单;原著扫描仅供改编取舍,不在大纲锁定前给所有原著角色批量出图。

Step 6 — 第二趟出卡

每个角色一份,同样能并发就并发。

每份任务拿到:

  • {baseDir}/references/profile-pass.md 和 {baseDir}/references/schema.md(读它们,照着做)
  • 报告语言 lang(Step 0 定的)
  • 该角色归并后的 name / aliases / notes / quotes
  • 同批其他角色的名字(避免长相声线撞车)

角色卡 JSON 写到 <workdir>/card-<slug>.json。断点续跑:只有对应源文、角色去留、设计与画风未变化时,才复用已存在的角色卡。

同时写一段故事摘要:用 lang 指定的语言,3–5 句,交代时空背景、核心情境、这几个人聚在一起的由头。短篇直接从原文写;长篇从各块的 roster note 归纳。不剧透结局,不写成推荐语。写到 <workdir>/summary.txt。非内置语言的话,把 Step 0 翻好的 ui 整块存成 <workdir>/ui.json。

然后合成 cast.json——用 assemble,不要手拼(手拼会丢字段、写错顶层键):

bash
node {baseDir}/scripts/novel-characters.mjs assemble <workdir> \
  --source <书名> --lang <lang> --style <style> \
  --out <输出目录>/<书名>-cast.json

坏卡会被逐个点名——哪份 card-*.json 坏了就只重跑那个角色,其他不用动。

同档角色的先后是戏份顺序,来自 Step 4 留下的 <workdir>/merged.json(assemble 自动读,也可用 --order 指别的文件)。报告左栏「按戏份排序」的序号就靠它——看到「同档角色将按文件名序」的警告说明 merged.json 丢了,回 Step 4 重新生成。

Step 7 — 校验 ⛔ 不能跳
bash
node {baseDir}/scripts/novel-characters.mjs validate <cast.json> <book.txt>

记得带上 --lang(Step 0 定的)。检查:结构、importance 枚举、引文逐字、出图提示词不含人名、语言分工(人类字段跟随 lang、出图/TTS 提示词永远英文)、以及非内置语言必须带 ui。

有违规就按报错逐条修,改完重跑,直到通过。 这四类错模型真的会犯——这套检查就是被真实输出打出来的。

Step 8 — 出图(可选,每个角色都出)

每个角色一张,用 image.sheet,落到 ./images/<slug>-sheet.png。一张横构图内部左右分栏:

┌──────────┬────────────────────────────┐
│  半身像   │   正视    侧视    背视       │
│ (证件照) ├────────────────────────────┤
│  面部基准  │  细节 · 细节 · 细节 · 细节   │
│   ~34%   │            16:9            │
└──────────┴────────────────────────────┘

左栏半身像是面部设计基准,右上三视图的脸照它画,右下是关键细节的小特写。两条硬要求:三视图的脸必须与半身像一致(否则一张图两个长相);三个全身像的比例必须协调(模型会为了塞下细节把人压扁)。

读 {baseDir}/references/sheet.md,照它的调用契约做。要点:

  • 没有 codex 就整步跳过,只交提示词,后面照常走
  • 跑在 codex 里就直接用 $imagegen;跑在别处就 shell 调 codex,先按那里的脚本探测版本最高的 binary(旧版会直接报错)
  • 一个角色一次调用,绝不批量
  • 单个失败就跳过,不阻断;最后汇总说明
  • 断点续跑:先检查母本、服装和画风是否变化;仅复用当前版本仍适用的图,失败或过期才补做

出图数量由已授权范围和当前制作批次决定:先做主角及本批关键配角的样张验证风格,再补其余需要跨镜保持身份的角色;功能性背景人物按群体规范处理。用户已明确要求全角色出图时按约执行,不重复索取相同授权。声线文字只是设计方向,不等于已生成或已批准的声音母版。

Step 9 — 输出
bash
cd <输出目录>
node {baseDir}/scripts/novel-characters.mjs render <cast.json> --md   > <书名>-cast.md
node {baseDir}/scripts/novel-characters.mjs render <cast.json> --html > report.html

语言取 cast.json 里的 lang,要临时覆盖就加 --lang <code>。

render 会自动去 images/<slug>-sheet.png 找图。所以先出图再 render。

report.html 的样式约定见 {baseDir}/references/report-style.md——要改样式先读它,别把它改回通用卡片墙。

最终落地:

<输出目录>/
├── <书名>-cast.json
├── <书名>-cast.md
├── report.html                    ← 双击就能开
└── images/
    └── <slug>-sheet.png           ← 有 codex 才有
Step 10 — 汇报

一句话说清:角色数、出图数、报告路径。校验一次没过的话,说明修了什么。有角色出图失败、被截断、或因为没有 codex 而没出图,明确说清楚。


边界

  • 单次上限 24 块(净覆盖约 93 万字符),超了会明确报 truncated,不静默截断
  • 人类可读字段跟随 --lang(默认中文);出图和 TTS 提示词永远英文,那些引擎吃英文最稳
  • 设定图最容易出的两个问题:一张图里两个长相、为了塞细节把人物压扁。拿到图先扫一眼,见 references/sheet.md
  • 出图只走 codex built-in $imagegen。不用它的 CLI fallback(要 OPENAI_API_KEY)
  • 想要能实时编辑、边跑边看的交互界面,那是另一个东西,不在这个 skill 里

自测

bash
node {baseDir}/scripts/selftest.mjs

310 项断言,不调模型、不花额度,覆盖分块 / 归并 / 合成 / 多语言 / 校验 / 渲染的全部确定性逻辑。改完脚本先跑这个。

自带样例

{baseDir}/examples/渡口.txt 是一篇短故事,4 个角色,其中货郎全程只有绰号、船夫只被叫过「老伯」——专门用来验别名归并。对应产出 渡口-cast.json / 渡口-cast.md 可以当质量基准,也是校验的自检夹具。

制作交接

独立使用时,自检后主动打开当前报告并给绝对路径链接,说明本轮范围、检查重点和下一步;需要锁定内容时在对话中收取通过或修改结论。已有确认覆盖当前版本就不重复询问,打开页面或下载 JSON 不算批准。总控已接管时,由总控统一收取这次结论,不另开重复审批。当前内容、依赖或源图改变后,不因旧文件仍存在就跳过复核;输出新版本并保留原审阅笔记。

本项目的阶段职责、变更记录和交付顺序由 short-drama-production 的 references/company-workflow.md 统一维护;未安装总控时按本 skill 的输入和交付范围独立完成,不将总控变成硬依赖。

涉及尚未授权的创作取舍时,给用户 2–3 个有具体差异的选项,说明收益、损失与推荐,允许保留原稿或自定义。模型先完成阅读、诊断和短样段,不把准备工作推给用户;已经明确授权的范围直接执行。未经用户选择,不把暂定片长预算升级成删词、删情绪段落的理由。

© suihe1, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 15 other files (scripts, references, assets) in skills/novel-characters of suihe1/short-drama-production.

  • SKILL.md
  • README.en.md
  • README.md
  • assets/report.webp
  • assets/sheet.jpg
  • examples/渡口-cast.json
  • examples/渡口-cast.md
  • examples/渡口.txt
  • references/profile-pass.md
  • references/report-style.md
  • references/roster-pass.md
  • references/schema.md
  • references/sheet.md
  • references/style-presets.md
  • scripts/novel-characters.mjs
  • scripts/selftest.mjs

Open the folder on GitHubat commit dbd3310

Compare with similar skills

Novel Characters next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Novel Characters compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Novel Characters this skillsuihe1/short-drama-production181—~1.8kAutomated safety check: NotesApache-2.0
Novel Storyboardeternityspring/shuohao-skills4.3k—~1.8kAutomated safety check: NotesApache-2.0
Short Drama Novel Analyzezenstory-ai/drama-skills2.7k—~1.9kAutomated safety check: PassMIT
Storyboard Managerailabs-393/ai-labs-claude-skills4551 repos~4.6kAutomated safety check: PassMIT
Story To Video WorkflowUtopai-Research/pai-code357—~2kAutomated safety check: PassCustom licence
Pneuma Plotwisepandazki/pneuma-skills161—~8.9kAutomated safety check: PassMIT

Similar skills

  • Novel Storyboard

    eternityspring/shuohao-skills

    给 AI 短剧出分镜:三层结构——段(一次视频生成,≤15 秒)→ 分镜(段内 2–5 秒的剪切,认领剧本节拍) → 分镜图(每切一张关键帧:主分镜图钉 0.00 秒,子分镜图钉各自切点)。

    4.3k GitHub stars~1.8k tokensUpdated 2 days ago
    Media & CreativeAuto-check: notes
  • Short Drama Novel Analyze

    zenstory-ai/drama-skills

    把长篇小说、连载网文或多集散稿拆成可追溯的原著分析:章节索引、改编价值快评、逐章功能提取、剧情单元与节奏聚合、人物与设定归并,最后给出改编价值判定与分集候选,交给 $short-drama-develop 立契约。用户说“导入这本小说”“拆这本书”“分析原著”“这本书能不能改短剧”“先看看值不值得拆”“把长篇拆成分集候选”,或直接给出小说文件路径时使用。只做只读的结构化分析,不写剧本、不建资产、…

    2.7k GitHub stars~1.9k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed
  • Storyboard Manager

    ailabs-393/ai-labs-claude-skills

    Assist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking.

    455 GitHub starsUsed in 1 repo~4.6k tokens
    Media & CreativeAuto-check passed
  • Story To Video Workflow

    Utopai-Research/pai-code

    Orchestrates story, script, screenplay, concept, product promo, and multi-shot idea work into finished video.

    357 GitHub stars~2k tokensUpdated 11 days ago
    Media & CreativeAuto-check passed
  • Pneuma Plotwise

    pandazki/pneuma-skills

    Pneuma Plotwise workspace guidelines. An agent skill from pandazki/pneuma-skills.

    161 GitHub stars~8.9k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Emotion Performance Director

    kangarooking/director-skills

    A skill your agent uses when the user wants to design, rewrite, refine, or vary emotional acting prompts for live-action AI video characters.

    181 GitHub stars~2.4k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed

More from suihe1/short-drama-production

  • Novel Art

    suihe1/short-drama-production

    为 AI 短剧设计场景和叙事道具母本、光照与状态变体,产出 art.json、Markdown、评审报告和可选设定图。用于美术设定、场景与道具一致性;不代替导演调度或成片人流设计。

    181 GitHub stars~1.3k tokensUpdated 25 days ago
    Auto-check: notes
  • Novel Outline

    suihe1/short-drama-production

    把小说或故事改编为短剧大纲,确定人物去留、分集因果、剧情重点与资产预算,产出可校验 JSON、Markdown 和评审报告。用于短剧大纲、改编方案和现有大纲诊断;不写完整剧本或镜头方案。

    181 GitHub stars~1.3k tokensUpdated 25 days ago
    Auto-check: notes
  • Novel Script

    suihe1/short-drama-production

    将分集大纲写成结构化场次、动作节拍和逐句台词,核对人物与美术引用、估算时长并交付剧本评审报告。用于写剧本、对白和场次修订;不分镜、不直接执行配音或视频生成。

    181 GitHub stars~658 tokensUpdated 25 days ago
    Auto-check: notes
  • Novel Storyboard

    suihe1/short-drama-production

    将剧本与导演意图转成生成段、逐镜时间、参考素材计划和可校验分镜报告;使用官方 h3-prompt-writing 编写 H3 提示词,可导出投产包。用于技术分镜、镜头表和分镜修订;生成视频须另有明确任务与成本授权,不负责最终选片或剪辑。

    181 GitHub stars~2.1k tokensUpdated 25 days ago
    Auto-check: notes
  • Short Drama Production

    suihe1/short-drama-production

    统筹 AI 短剧的阶段、依赖、审批、H3 任务、声音资产、粗剪和 QC,并用 production.json 追踪返工;默认支持 16:9。用于整部短剧生产、继续项目、状态检查或上游变更影响分析;单独创作大纲、角色、美术、剧本或分镜时使用对应专业 skill。

    181 GitHub stars~1.1k tokensUpdated 25 days ago
    Auto-check passed
  • Short Drama Director

    suihe1/short-drama-production

    把剧本转成表演、场面调度、镜头覆盖、景别、机位、运镜与剪辑意图,产出可校验导演镜头包。用于导演方案、拍法、镜头诊断和分镜重构;只要求大纲、剧本或资产设定时不触发。

    181 GitHub stars~1.2k tokensUpdated 25 days ago
    Auto-check passed

Works with

Questions about Novel Characters

What does Novel Characters do?

从故事中整理人物身份、关系、外观和声线设计,产出角色卡、图像提示词与评审报告,可按需生成设定图。用于角色分析、人物画像和角色母本;短剧制作中按已批准大纲与当前批次选角。. Novel Characters is an agent skill from suihe1/short-drama-production.

When should I use Novel Characters?

Novel Characters fits situations like: tasks that involve Creative writing and fiction.

How do I install Novel Characters in Claude Code?

Run `npx skills add suihe1/short-drama-production --skill novel-characters -a claude-code`. Or copy the skill folder (skills/novel-characters in suihe1/short-drama-production) into .claude/skills/novel-characters in your project. Claude Code loads it when a task matches its description.

How do I install Novel Characters in Codex?

Run `npx skills add suihe1/short-drama-production --skill novel-characters -a codex`. Or copy the skill folder (skills/novel-characters in suihe1/short-drama-production) into .agents/skills/novel-characters in your project. Codex loads it when a task matches its description.

Can I use Novel Characters in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add suihe1/short-drama-production --skill novel-characters -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/novel-characters, .gemini/skills/novel-characters, .github/skills/novel-characters and .opencode/skills/novel-characters in your project.

What does Novel Characters need to run?

Going by SKILL.md and its folder, Novel Characters needs JavaScript for the scripts in its folder, the command-line tools its instructions call (node) and credentials named OPENAI_API_KEY. Our summary lists: Node.js; A credential in OPENAI_API_KEY. Its frontmatter pre-approves these tools: Read, Write, Bash, Task, Glob.

Does Novel Characters access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Novel Characters safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Novel Characters use?

Novel Characters is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Novel Characters use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.8k tokens, read only when the agent opens those files.

What are the alternatives to Novel Characters?

Skills that share tags, products or a category with Novel Characters: Novel Storyboard (eternityspring/shuohao-skills, 4.3k stars), Short Drama Novel Analyze (zenstory-ai/drama-skills, 2.7k stars), Storyboard Manager (ailabs-393/ai-labs-claude-skills, 455 stars) and Story To Video Workflow (Utopai-Research/pai-code, 357 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Novel Characters?

suihe1 (a GitHub user) maintains it in suihe1/short-drama-production, which has 181 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 16, 2026.

Source: suihe1/short-drama-production on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.